# Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech

arXiv: https://arxiv.org/abs/2106.01625 · HTML: https://mlsanity.com/paper/2106.01625/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 69 references that are in the map.
- First posted on arXiv 3 Jun 2021.

## Builds on (most cited first, 30 of 42)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance](https://mlsanity.com/paper/1909.02622/) (2019)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://mlsanity.com/paper/1605.06069/) (2016)
- [Training Very Deep Networks](https://mlsanity.com/paper/1507.06228/) (2015)
- [What makes a good conversation? How controllable attributes affect human judgments](https://mlsanity.com/paper/1902.08654/) (2019)
- [A Benchmark Dataset for Learning to Intervene in Online Hate Speech](https://mlsanity.com/paper/1909.04251/) (2019)
- [Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization](https://mlsanity.com/paper/1809.05972/) (2018)
- [CONAN -- COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech](https://mlsanity.com/paper/1910.03270/) (2019)
- [Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images](https://mlsanity.com/paper/1703.10660/) (2017)
- [A Neural Network Approach to Context-Sensitive Generation of Conversational Responses](https://mlsanity.com/paper/1506.06714/) (2015)
- [Do Massively Pretrained Language Models Make Better Storytellers?](https://mlsanity.com/paper/1909.10705/) (2019)
- [Thou shalt not hate: Countering Online Hate Speech](https://mlsanity.com/paper/1808.04409/) (2018)
- [Long and Diverse Text Generation with Planning-based Hierarchical Variational Model](https://mlsanity.com/paper/1908.06605/) (2019)
- [Spread of hate speech in online social media](https://mlsanity.com/paper/1812.01693/) (2018)
- [Generating Counter Narratives against Online Hate Speech: Data and Strategies](https://mlsanity.com/paper/2004.04216/) (2020)

## Built on by (most cited first, 30 of 42)

- [Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering](https://mlsanity.com/paper/2211.03433/) (2022)
- [Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation](https://mlsanity.com/paper/2303.06433/) (2023)
- [SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures](https://mlsanity.com/paper/2110.07518/) (2021)
- [Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study](https://mlsanity.com/paper/2204.01440/) (2022)
- [CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeech](https://mlsanity.com/paper/2205.04304/) (2022)
- [Beyond Denouncing Hate: Strategies for Countering Implied Biases and Stereotypes in Language](https://mlsanity.com/paper/2311.00161/) (2023)
- [NLP for Counterspeech against Hate: A Survey and How-To Guide](https://mlsanity.com/paper/2403.20103/) (2024)
- [Understanding Counterspeech for Online Harm Mitigation](https://mlsanity.com/paper/2307.04761/) (2023)
- [On Zero-Shot Counterspeech Generation by LLMs](https://mlsanity.com/paper/2403.14938/) (2024)
- [Contextualized Counterspeech: Strategies for Adaptation, Personalization, and Evaluation](https://mlsanity.com/paper/2412.07338/) (2024)
- [DisCGen: A Framework for Discourse-Informed Counterspeech Generation](https://mlsanity.com/paper/2311.18147/) (2023)
- [Counterspeeches up my sleeve! Intent Distribution Learning and Persistent Fusion for Intent-Conditioned Counterspeech Generation](https://mlsanity.com/paper/2305.13776/) (2023)
- [Outcome-Constrained Large Language Models for Countering Hate Speech](https://mlsanity.com/paper/2403.17146/) (2024)
- [Multilingual Counter Narrative Type Classification](https://mlsanity.com/paper/2109.13664/) (2021)
- [HateRephrase: Zero- and Few-Shot Reduction of Hate Intensity in Online Posts using Large Language Models](https://mlsanity.com/paper/2310.13985/) (2023)
- [ELF22: A Context-based Counter Trolling Dataset to Combat Internet Trolls](https://mlsanity.com/paper/2208.00176/) (2022)
- [Weigh Your Own Words: Improving Hate Speech Counter Narrative Generation via Attention Regularization](https://mlsanity.com/paper/2309.02311/) (2023)
- [Basque and Spanish Counter Narrative Generation: Data Creation and Evaluation](https://mlsanity.com/paper/2403.09159/) (2024)
- [A Multi-Aspect Framework for Counter Narrative Evaluation using Large Language Models](https://mlsanity.com/paper/2402.11676/) (2024)
- [Low-Resource Counterspeech Generation for Indic Languages: The Case of Bengali and Hindi](https://mlsanity.com/paper/2402.07262/) (2024)
- [CrowdCounter: A benchmark type-specific multi-target counterspeech dataset](https://mlsanity.com/paper/2410.01400/) (2024)
- [Assessing the Human Likeness of AI-Generated Counterspeech](https://mlsanity.com/paper/2410.11007/) (2024)
- [The State of Profanity Obfuscation in Natural Language Processing](https://mlsanity.com/paper/2210.07595/) (2022)
- [The crime of being poor](https://mlsanity.com/paper/2303.14128/) (2023)
- [CSEval: Towards Automated, Multi-Dimensional, and Reference-Free Counterspeech Evaluation using Auto-Calibrated LLMs](https://mlsanity.com/paper/2501.17581/) (2025)
- [WLV-RIT at GermEval 2021: Multitask Learning with Transformers to Detect Toxic, Engaging, and Fact-Claiming Comments](https://mlsanity.com/paper/2108.00057/) (2021)
- [Challenging Negative Gender Stereotypes: A Study on the Effectiveness of Automated Counter-Stereotypes](https://mlsanity.com/paper/2404.11845/) (2024)
- [Towards Effective Counter-Responses: Aligning Human Preferences with Strategies to Combat Online Trolling](https://mlsanity.com/paper/2410.04164/) (2024)
- [Towards Countering Essentialism through Social Bias Reasoning](https://mlsanity.com/paper/2303.16173/) (2023)
- [Consolidating Strategies for Countering Hate Speech Using Persuasive Dialogues](https://mlsanity.com/paper/2401.07810/) (2024)

## Abstract (arXiv)

Countermeasures to effectively fight the ever increasing hate speech online without blocking freedom of speech is of great social interest. Natural Language Generation (NLG), is uniquely capable of developing scalable solutions. However, off-the-shelf NLG methods are primarily sequence-to-sequence neural models and they are limited in that they generate commonplace, repetitive and safe responses regardless of the hate speech (e.g., "Please refrain from using such language.") or irrelevant responses, making them ineffective for de-escalating hateful conversations. In this paper, we design a three-module pipeline approach to effectively improve the diversity and relevance. Our proposed pipeline first generates various counterspeech candidates by a generative model to promote diversity, then filters the ungrammatical ones using a BERT model, and finally selects the most relevant counterspeech response using a novel retrieval-based method. Extensive Experiments on three representative datasets demonstrate the efficacy of our approach in generating diverse and relevant counterspeech.